{"id":"https://openalex.org/W4281731876","doi":"https://doi.org/10.1007/s43684-022-00029-z","title":"Two-stage reward allocation with decay for multi-agent coordinated behavior for sequential cooperative task by using deep reinforcement learning","display_name":"Two-stage reward allocation with decay for multi-agent coordinated behavior for sequential cooperative task by using deep reinforcement learning","publication_year":2022,"publication_date":"2022-05-27","ids":{"openalex":"https://openalex.org/W4281731876","doi":"https://doi.org/10.1007/s43684-022-00029-z"},"language":"en","primary_location":{"id":"doi:10.1007/s43684-022-00029-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s43684-022-00029-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s43684-022-00029-z.pdf","source":{"id":"https://openalex.org/S4210227358","display_name":"Autonomous Intelligent Systems","issn_l":"2730-616X","issn":["2730-616X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Intelligent Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://link.springer.com/content/pdf/10.1007/s43684-022-00029-z.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062824084","display_name":"Yuki Miyashita","orcid":"https://orcid.org/0000-0002-1676-9346"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]},{"id":"https://openalex.org/I26725883","display_name":"Shimizu (Japan)","ror":"https://ror.org/039zveh30","country_code":"JP","type":"company","lineage":["https://openalex.org/I26725883"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuki Miyashita","raw_affiliation_strings":["Department of Computer Science and Communications Engineering, Waseda University, Tokyo, 1698555, Japan","Shimizu Corporation, Tokyo, 1048370, Japan"],"raw_orcid":"https://orcid.org/0000-0002-1676-9346","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Communications Engineering, Waseda University, Tokyo, 1698555, Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Shimizu Corporation, Tokyo, 1048370, Japan","institution_ids":["https://openalex.org/I26725883"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082205147","display_name":"Toshiharu Sugawara","orcid":"https://orcid.org/0000-0002-9271-4507"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshiharu Sugawara","raw_affiliation_strings":["Department of Computer Science and Communications Engineering, Waseda University, Tokyo, 1698555, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Communications Engineering, Waseda University, Tokyo, 1698555, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5062824084"],"corresponding_institution_ids":["https://openalex.org/I150744194","https://openalex.org/I26725883"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.05528164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"2","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9678000211715698,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.9624999761581421,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8222033977508545},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.766264796257019},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7647252082824707},{"id":"https://openalex.org/keywords/division","display_name":"Division (mathematics)","score":0.500011682510376},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4997532367706299},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4842042922973633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4802427589893341},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10419100522994995},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09584251046180725},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07012695074081421},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.0681372880935669},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.059722065925598145}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8222033977508545},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.766264796257019},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7647252082824707},{"id":"https://openalex.org/C60798267","wikidata":"https://www.wikidata.org/wiki/Q1226939","display_name":"Division (mathematics)","level":2,"score":0.500011682510376},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4997532367706299},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4842042922973633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4802427589893341},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10419100522994995},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09584251046180725},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07012695074081421},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0681372880935669},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.059722065925598145},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s43684-022-00029-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s43684-022-00029-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s43684-022-00029-z.pdf","source":{"id":"https://openalex.org/S4210227358","display_name":"Autonomous Intelligent Systems","issn_l":"2730-616X","issn":["2730-616X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Intelligent Systems","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6f38562147ca433b9b1f5be0d6eb883e","is_oa":false,"landing_page_url":"https://doaj.org/article/6f38562147ca433b9b1f5be0d6eb883e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Autonomous Intelligent Systems, Vol 2, Iss 1, Pp 1-18 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1007/s43684-022-00029-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s43684-022-00029-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s43684-022-00029-z.pdf","source":{"id":"https://openalex.org/S4210227358","display_name":"Autonomous Intelligent Systems","issn_l":"2730-616X","issn":["2730-616X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Autonomous Intelligent Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4757044010","display_name":"Improving sustainability, flexibility, and robustness of artifactitious systems using emergence of divisional cooperation","funder_award_id":"17KT0044","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8234754435","display_name":"Studies on autonomous learning of agents' organizational formation for system efficiency","funder_award_id":"20H04245","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281731876.pdf","grobid_xml":"https://content.openalex.org/works/W4281731876.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2099618002","https://openalex.org/W2103551861","https://openalex.org/W2119053738","https://openalex.org/W2169560253","https://openalex.org/W2539402368","https://openalex.org/W2575705757","https://openalex.org/W2768629321","https://openalex.org/W2911495555","https://openalex.org/W2913251325","https://openalex.org/W2913668833","https://openalex.org/W2913756371","https://openalex.org/W2914782308","https://openalex.org/W2963890729","https://openalex.org/W2981366899","https://openalex.org/W3106986375","https://openalex.org/W3117280628","https://openalex.org/W3149322120","https://openalex.org/W4212774754","https://openalex.org/W4232967792","https://openalex.org/W6600297719","https://openalex.org/W6633099067","https://openalex.org/W6743505604","https://openalex.org/W6810641125","https://openalex.org/W6819060087"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4206669594","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W2909304650","https://openalex.org/W3111983280","https://openalex.org/W3164468573","https://openalex.org/W2185410470"],"abstract_inverted_index":{"Abstract":[0],"We":[1],"propose":[2],"a":[3,38,72,137],"two-stage":[4,162],"reward":[5,78,158,189],"allocation":[6],"method":[7,20,97,174],"with":[8,132,183],"decay":[9],"using":[10,153],"an":[11,81,133],"extension":[12],"of":[13,60,111,152,156],"replay":[14],"memory":[15],"to":[16,26,53,88,91,99,181],"adapt":[17],"this":[18],"rewarding":[19],"for":[21,30,57,68,83],"deep":[22],"reinforcement":[23],"learning":[24],"(DRL),":[25],"generate":[27,100],"coordinated":[28,69,127,194],"behaviors":[29,70,103],"tasks":[31],"that":[32,171],"can":[33,139,191],"be":[34,140],"completed":[35],"by":[36,42,107,143],"executing":[37],"few":[39],"subtasks":[40],"sequentially":[41,142],"heterogeneous":[43,145],"agents.":[44],"An":[45],"independent":[46],"learner":[47],"in":[48,104,160],"cooperative":[49],"multi-agent":[50,105],"systems":[51],"needs":[52],"learn":[54,92],"its":[55,61],"policies":[56],"effective":[58],"execution":[59,130],"own":[62],"responsible":[63],"subtask,":[64],"as":[65,67],"well":[66],"under":[71],"certain":[73],"coordination":[74],"structure.":[75],"Although":[76],"the":[77,109,118,126,150,157,161,165,172,177,184],"scheme":[79],"is":[80,86],"issue":[82],"DRL,":[84],"it":[85,90],"difficult":[87],"design":[89],"both":[93],"policies.":[94],"Our":[95],"proposed":[96,173],"attempts":[98],"these":[101],"different":[102],"DRL":[106],"dividing":[108],"timing":[110],"rewards":[112],"into":[113],"two":[114,144],"stages":[115],"and":[116,129,190],"varying":[117],"ratio":[119],"between":[120],"them":[121],"over":[122],"time.":[123],"By":[124],"introducing":[125],"delivery":[128],"problem":[131],"expiration":[134],"time,":[135],"where":[136],"task":[138],"executed":[141],"agents,":[146],"we":[147],"experimentally":[148],"analyze":[149],"effect":[151],"various":[154],"ratios":[155],"division":[159],"allocations":[163],"on":[164],"generated":[166],"behaviors.":[167],"The":[168],"results":[169],"demonstrate":[170],"could":[175],"improve":[176],"overall":[178],"performance":[179],"relative":[180],"those":[182],"conventional":[185],"one-time":[186],"or":[187],"fixed":[188],"establish":[192],"robust":[193],"behavior.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}